1. A method (400) for optimizing transmission of user relevant events, the method (400)
comprising:
5 generating (402), by a first Artificial Intelligence (AI) model, an event metadata (312) for
a user relevant event from an event snippet (310) of the user relevant event, wherein the event
snippet (310) is obtained from a multimedia content, and wherein the multimedia content
comprises at least one of an audio stream or a video stream;
transmitting (404), by the first AI model to a second AI model, the event metadata (312)
10 associated with the user relevant event, wherein the event metadata (312) comprises a set of frames
associated with the user relevant event, a start timestamp and an end time stamp associated with
the user relevant event, and key information associated with the user relevant event; and
reconstructing (406), by the second AI model, a segment of the multimedia content
associated with the user relevant event based on the event metadata (312).
15
2. The method (400) as claimed in claim 1, wherein generating (402) the event metadata (312)
comprises:
receiving(502), by the first AI model, the multimedia content from at least one of a plurality
of sources;
20 identifying (504), by the first AI model, the user relevant event from the multimedia
content based on an associated set of event parameters (308); and
upon identifying (504), extracting (506), by the first AI model, the event snippet (310) of
the user relevant event from the multimedia content to generate the event metadata (312).
25 3. The method (500) as claimed in claim 2, comprising:
upon identifying (504) the user relevant event, extracting (508), by the first AI model, the
start timestamp and the end timestamp, and the key information associated with the user relevant
event.
24
4. The method (500) as claimed in claim 2, wherein the first AI model is trained to detect user
relevant events based on a plurality of training event parameters associated with a plurality of
training events.
5 5. The method (400) as claimed in claim 1, wherein the segment of the multimedia content
associated with the user relevant event is reconstructed based on an image diffusion technique
(318).
6. The method (400) as claimed in claim 1, wherein reconstructing (406) the segment of the
10 multimedia content comprises:
receiving (602), by the second AI model, a user input corresponding to the user relevant
event;
retrieving (604), by the second AI model, the event metadata (312) corresponding to the
user relevant event from the first AI model, upon receiving (602) the user input; and
15 utilizing (606), by the second AI model, the event metadata (312) to generate the segment
of the multimedia content corresponding to the user relevant event.
7. The method (400) as claimed in claim 1, comprising:
presenting (408), via a Graphical User Interface (GUI), the segment of the multimedia
20 content to a user.
8. A system (100) for optimizing transmission of user relevant events, the system (100)
comprising:
a processing circuitry (202, 210); and
25 a memory (204, 212) communicatively coupled to the processing circuitry (202, 210),
wherein the memory (204, 212) stores processor-executable instructions, which, on execution,
causes the processing circuitry (202, 210) to:
generate (402) an event metadata (312) for a user relevant event from an event
snippet (310) of the user relevant event by a first Artificial Intelligence (AI) model, wherein
30 the event snippet (310) is obtained from a multimedia content, and wherein the multimedia
content comprises at least one of an audio stream or a video stream;
25
transmit (404) the event metadata (312) associated with the user relevant event by
the first AI model to a second AI model, wherein the event metadata (312) comprises a set
of frames associated with the user relevant event, a start timestamp and an end time stamp
associated with the user relevant event, and key information associated with the user
5 relevant event; and
reconstruct (406) a segment of the multimedia content associated with the user
relevant event based on the event metadata (312) by the second AI model.
9. The system (100) as claimed in claim 1, wherein, to generate (402) the event metadata (312),
10 the processor instructions, on execution, causes the processing circuitry (202) to:
receive (502), by the first AI model, the multimedia content from at least one of a plurality
of sources;
identify (504), by the first AI model, the user relevant event from the multimedia content
based on an associated set of event parameters (308); and
15 upon identifying (504), extract (506), by the first AI model, the event snippet (310) of the
user relevant event from the multimedia content to generate the event metadata (312).
10. The system (100) as claimed in claim 9, wherein the processor instructions, on execution, cause
the processing circuitry (202) to:
20 upon identifying (504) the user relevant event, extract (508), by the first AI model, the start
timestamp and the end timestamp, and the key information associated with the user relevant event.